As part of its efforts to better improve its risk management systems, ANZ announced its partnership with Nvidia and Monash University researchers in developing deep learning techniques to assess loan serviceability.
According to a Computerworld report, ANZ's proof of concept will use a "neural network to predict which customers were likely to default on payments."
Speaking at the Nvidia AI Conference in Sydney, ANZ head of retail risk Jason Humphrey said this will augment the two methods traditionally used by banks to assess risk, the application scoring and the behaviour scoring.
"Once you start seeing the behaviour of a customer making payment on a product it becomes very predictive and very powerful at predicting whether the customer is going to continue making those payments on that product," he said, as quoted by Computerworld.
While the behavioural scoring is essentially more efficient than the application scoring method, Humphrey said there are limitations from the availability, accuracy, and amount of data.
This is what the proof of concept wants to address. Humphrey said the bank tested the technology by using credit card information from 1 million accounts.
“The way behaviour scoring works today is at the start of the month you receive a risk, at the end of the month that risk updates. When you go to daily scoring, all of a sudden with ongoing scores you can see the behaviour changing quite a bit... you can see risk changing more dynamically," he said.
He furthered: "The key to risk management, banking and finance is time: The quicker you can resolve a problem, the quicker you minimise any loss, inconvenience, or degradation of customer experience.”
Collections: Mortgage News